funasr pages

游雁

2023-11-16 4ace5a95b052d338947fc88809a440ccd55cf6b4

 egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer.py

@@ -16,13 +16,13 @@
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
    else:
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch",
        output_dir=output_dir_job,
    )
    audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
    inference_pipline(audio_in=audio_in)
    inference_pipeline(audio_in=audio_in)


def modelscope_infer(params):
@@ -74,7 +74,7 @@
    # If text exists, compute CER
    text_in = os.path.join(params["data_dir"], "text")
    if os.path.exists(text_in):
        text_proc_file = os.path.join(best_recog_path, "token")
        text_proc_file = os.path.join(best_recog_path, "text")
        compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer"))